Abstract
In the realm of automatic question-answering (Q&A) for technical communities, accurately perceiving and predicting user intent is a crucial step towards improving Q&A system performance by integrating user intention with answer reasoning processes. We conducted research into intent understanding at the sentence level, aiming to clarify the function of each sentence in technical Q&A communities and improve the system's response accuracy. To address the shortcomings of existing research, which typically ignores information such as speaker type and sentence position, we propose a multi-task learning framework to effectively utilize this information for sentence representation learning. By doing so, the model can acquire richer interactive question-answer language features, thereby enhancing the performance of intent label classification. Within this framework, we present two models: BA-multi and CCR-multi. Our validation experiments on the MSDialog-Intent dataset demonstrate that the multi-task learning model significantly outperforms both the baseline and feature extension models, achieving state-of-the-art performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We tried various thresholds in the range of 0.3 to 0.7, and found that each index was the best at 0.5.
References
Liu, X., He, P., Chen, W., et al.: Multi-task deep neural networks for natural language understanding. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4487–4496 (2019)
Deng, Y., Xie, Y., Li, Y., et al.: Multi-task learning with multi-view attention for answer selection and knowledge base question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6318–6325 (2019)
Trinh, T., Dai, A., Luong, T., et al.: Learning longer-term dependencies in RNNs with auxiliary losses. In: International Conference on Machine Learning, pp. 4965–4974 (2018)
Kacupaj, E., Plepi, J., Singh, K., et al.: Conversational question answering over knowledge graphs with transformer and graph attention networks. arXiv preprint arXiv:2104.01569 (2021)
Yu, Y., Peng, S., Yang, G.H.: Modeling long-range context for concurrent dialogue acts recognition. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2277–2280 (2019)
Ang, J., Liu, Y., Shriberg, E.: Automatic dialog act segmentation and classification in multiparty meetings. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2005), vol. 1 (2005)
Surendran, D., Levow, G.A.: Dialog act tagging with support vector machines and hidden Markov models. In: Ninth International Conference on Spoken Language Processing (2006)
Ji, G., Bilmes, J.: Dialog act tagging using graphical models. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2005), vol. 1 (2005)
Kim, S.N., Cavedon, L., Baldwin, T.: Classifying dialogue acts in one-on-one live chats. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 862–871 (2010)
Fernandez, R., Picard, R.W.: Dialog act classification from prosodic features using support vector machines. In: International Conference on Speech Prosody 2002 (2002)
Venkataraman, A., Ferrer, L., Stolcke, A., et al.: Training a prosody-based dialog act tagger from unlabeled data. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003), vol. 1 (2003)
Dielmann, A., Renals, S.: Recognition of dialogue acts in multiparty meetings using a switching DBN. IEEE Trans. Audio Speech Lang. Process. 16(7), 1303–1314 (2008)
Quarteroni, S., Ivanov, A.V., Riccardi, G.: Simultaneous dialog act segmentation and classification from human-human spoken conversations. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5596–5599 (2011)
Chen, L., Di Eugenio, B.: Multimodality and dialogue act classification in the RoboHelper project. In: Proceedings of the SIGDIAL 2013 Conference, pp. 183–192 (2013)
Ribeiro, E., Ribeiro, R., de Matos, D.M.: The influence of context on dialogue act recognition. arXiv preprint arXiv:1506.00839 (2015)
Barahona, L.M.R., Gasic, M., Mrki, N., et al.: Exploiting sentence and context representations in deep neural models for spoken language understanding. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 258–267 (2016)
Khanpour, H., Guntakandla, N., Nielsen, R.: Dialogue act classification in domain-independent conversations using a deep recurrent neural network. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2012–2021 (2016)
Liu, Y., Han, K., Tan, Z., et al.: Using context information for dialog act classification in DNN framework. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2170–2178 (2017)
Qu, C., Yang, L., Croft, W.B., et al.: User intent prediction in information-seeking conversations. In: Proceedings of the 2019 Conference on Human Information Interaction and Retrieval, pp. 25–33 (2019)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751 (2014)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. arXiv preprint arXiv:1505.00387 (2015)
Liu, J., Chang, W.C., Wu, Y., et al.: Deep learning for extreme multi-label text classification. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 115–124 (2017)
Acknowledgement
This study was supported by the National Natural Science Foundation of China (No. 62262029), the Natural Science Foundation of Jiangxi Province (No. 20212BAB202016), the Science and Technology Research Project of Jiangxi Provincial Department of Education (No. GJJ200318 and GJJ210520).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, X., Song, H., Lu, M. (2023). Intent Understanding for Automatic Question Answering in Network Technology Communities Based on Multi-task Learning. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds) Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023. Lecture Notes in Computer Science(), vol 13926. Springer, Cham. https://doi.org/10.1007/978-3-031-36822-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-36822-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36821-9
Online ISBN: 978-3-031-36822-6
eBook Packages: Computer ScienceComputer Science (R0)